文章基本信息

标题：Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation
本地全文：下载
作者：Youngchun Kwon ; Jiho Yoo ; Youn-Suk Choi 等
期刊名称：Journal of Cheminformatics
印刷版ISSN：1758-2946
电子版ISSN：1758-2946
出版年度：2019
卷号：11
期号：1
页码：1-10
DOI：10.1186/s13321-019-0396-x
出版社：BioMed Central
摘要：With the advancements in deep learning, deep generative models combined with graph neural networks have been successfully employed for data-driven molecular graph generation. Early methods based on the non-autoregressive approach have been effective in generating molecular graphs quickly and efficiently but have suffered from low performance. In this paper, we present an improved learning method involving a graph variational autoencoder for efficient molecular graph generation in a non-autoregressive manner. We introduce three additional learning objectives and incorporate them into the training of the model: approximate graph matching, reinforcement learning, and auxiliary property prediction. We demonstrate the effectiveness of the proposed method by evaluating it for molecular graph generation tasks using QM9 and ZINC datasets. The model generates molecular graphs with high chemical validity and diversity compared with existing non-autoregressive methods. It can also conditionally generate molecular graphs satisfying various target conditions.
关键词：Molecular graph ; Variational autoencoder ; Graph neural network ; Deep learning ;